Add web frontend with JWT auth, RBAC, SSE dashboard, and config editor

- FastAPI + htmx + Jinja2 web frontend, started with --web flag
- JWT HS256 auth (WEB_SECRET_KEY) with httpOnly cookies; access (15 min) +
  refresh (7 day) tokens; refresh rotation + JTI revocation in data/web.db
- RBAC: superadmin > admin > reader enforced per route
- Live SSE dashboard fed by tui/events broadcast queue
- Config editor: keyword groups and channel list saved to data/runtime_config.json
  and hot-reloaded in-process (scorer.reload_from_config, signal_channel_changed)
- config.py migrated to load groups/channels from runtime_config.json;
  falls back to hardcoded defaults when file absent
- tui/events.py: subscribe/unsubscribe broadcast, set_bot_context/signal_channel_changed
- utils/scorer.py: import config as _config (fixes local binding); reload_from_config()
- utils/database.py: count_by_severity, recent_for_domains, count_by_severity_for_domains
- 53 new tests (events bus, JWT lifecycle, web DB CRUD, RBAC enforcement,
  config round-trip); total 141 passing
This commit is contained in:
2026-04-02 11:41:46 -03:00
parent b28168c846
commit 4c104cddd2
32 changed files with 2093 additions and 47 deletions

View File

@@ -144,6 +144,51 @@ def by_severity(severity: str) -> list[sqlite3.Row]:
""", (severity,)).fetchall()
def recent_for_domains(patterns: list[str], limit: int = 100) -> list[sqlite3.Row]:
"""Return recent hits whose `raw` field matches any of the given regex-like patterns."""
if not patterns:
return []
conditions = " OR ".join("raw LIKE ?" for _ in patterns)
args = [f"%{p.replace(r'\.','.').replace('@','').replace('^','').replace('$','')}%" for p in patterns]
args.append(limit)
with _connect() as conn:
return conn.execute(
f"SELECT * FROM hits WHERE ({conditions}) ORDER BY timestamp DESC LIMIT ?",
args,
).fetchall()
def count_by_severity_for_domains(patterns: list[str]) -> dict:
"""Severity counts filtered to hits matching any of the given patterns."""
if not patterns:
return {"CRITICAL": 0, "HIGH": 0, "MEDIUM": 0, "LOW": 0}
conditions = " OR ".join("raw LIKE ?" for _ in patterns)
args = [f"%{p.replace(r'\.','.').replace('@','').replace('^','').replace('$','')}%" for p in patterns]
with _connect() as conn:
rows = conn.execute(
f"SELECT severity, COUNT(*) FROM hits WHERE ({conditions}) GROUP BY severity",
args,
).fetchall()
counts = {"CRITICAL": 0, "HIGH": 0, "MEDIUM": 0, "LOW": 0}
for row in rows:
if row[0] in counts:
counts[row[0]] = row[1]
return counts
def count_by_severity() -> dict:
"""Overall severity counts (unique hits only)."""
with _connect() as conn:
rows = conn.execute(
"SELECT severity, COUNT(*) FROM hits WHERE seen_before=0 GROUP BY severity"
).fetchall()
counts = {"CRITICAL": 0, "HIGH": 0, "MEDIUM": 0, "LOW": 0}
for row in rows:
if row[0] in counts:
counts[row[0]] = row[1]
return counts
def stats() -> dict:
"""Return summary statistics."""
with _connect() as conn:

View File

@@ -72,16 +72,20 @@ The URL field handles two common stealer-log complications:
---
## Module-level globals (rebuilt on import + via KeywordsScreen)
## Module-level globals (rebuilt on import + via reload_from_config)
| Name | Type | Description |
|------|------|-------------|
| `EMPLOYEE_DOMAINS` | `list[tuple[str, Pattern]]` | `(domain_str, anchored_pattern)` for `@`-keywords |
| `ORG_DOMAINS` | `list[Pattern]` | Plain domain patterns for all keywords |
scorer uses `import config as _config` (not `from config import TARGET_KEYWORDS`), so patching `config.TARGET_KEYWORDS` at runtime is sufficient — `_build_*` reads the live module attribute.
To rebuild after editing `config.TARGET_KEYWORDS` at runtime:
```python
import utils.scorer as scorer
scorer.EMPLOYEE_DOMAINS = scorer._build_employee_domains()
scorer.ORG_DOMAINS = scorer._build_org_domains()
scorer.reload_from_config()
```
### `reload_from_config() -> None`
Rebuilds `EMPLOYEE_DOMAINS` and `ORG_DOMAINS` from the current `config.TARGET_KEYWORDS`. Called by web config routes after `config.save_runtime_config()` writes new keyword groups.

View File

@@ -30,7 +30,7 @@ Each scored hit gets a dict with:
import re
import logging
from dataclasses import dataclass, field
from config import TARGET_KEYWORDS
import config as _config
log = logging.getLogger(__name__)
@@ -124,7 +124,7 @@ def _build_employee_domains() -> list[tuple[str, re.Pattern]]:
Returns list of (domain_str, compiled_pattern) tuples.
"""
patterns = []
for kw in TARGET_KEYWORDS:
for kw in _config.TARGET_KEYWORDS:
if "@" in kw:
domain = _kw_to_domain(kw)
if domain:
@@ -144,7 +144,7 @@ def _build_org_domains() -> list[re.Pattern]:
Checks that the org domain appears anywhere in the line.
"""
patterns = []
for kw in TARGET_KEYWORDS:
for kw in _config.TARGET_KEYWORDS:
domain = _kw_to_domain(kw)
if domain:
patterns.append(re.compile(re.escape(domain), re.IGNORECASE))
@@ -153,6 +153,16 @@ def _build_org_domains() -> list[re.Pattern]:
ORG_DOMAINS = _build_org_domains()
def reload_from_config() -> None:
"""
Rebuild EMPLOYEE_DOMAINS and ORG_DOMAINS from the current config.TARGET_KEYWORDS.
Call after save_runtime_config() updates the keyword list.
"""
global EMPLOYEE_DOMAINS, ORG_DOMAINS
EMPLOYEE_DOMAINS = _build_employee_domains()
ORG_DOMAINS = _build_org_domains()
# ─── Scoring logic ────────────────────────────────────────────────────────────